S Raut
Principal Member Of Technical Staff at AMD
Bengaluru, Karnataka, India
Summary
🎓
Top SchoolS Raut is a Principal Member of Technical Staff at AMD with eight years of focused R&D experience designing and optimizing high-performance software libraries for FFTs, linear algebra, and multimedia signal processing. He has a strong track record of low-level performance engineering across single-core, multi-core and distributed systems, including concrete contributions to well-known projects such as AMD-FFTW and BLIS where he optimized TRSM, GEMM and SYRK kernels for Zen/EPYC architectures. His background spans video, image, speech and radar processing, combining algorithmic research with production-grade implementation and benchmarking. Based in Bengaluru, he brings a pragmatic systems view—tuning blocking, precision and multi-instance behavior—to extract real-world throughput gains on modern CPUs.
7 years of coding experience
16 years of employment as a software developer
Bachelor of Engineering (B.E.) Electrical Electronics and Communications Engineering, Bachelor of Engineering (B.E.) Electrical Electronics and Communications Engineering at Balasore College of Engg. and Tech.
English, Odia, Hindi, Japanese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
c1710
matrix-multiplication10
cluster-computing10
parallel-computing10
c1110
blas10
performance-optimization10
scientific-computing10
linear-algebra10
assembler9
assembly9
Programming languages (1)
Github contributions (5)
flame/blis
Jun 2018 - Dec 2018
BLAS-like Library Instantiation Software Framework
Role in this project:
Back-end Developer / Performance Engineer
Back-end Developer / Performance EngineerContributions:13 commits in 6 months
Contributions summary:S primarily focused on optimizing the BLIS (BLAS-like Library Instantiation Software Framework) library, specifically for small matrix operations and Zen architecture. Their contributions include implementing and optimizing small TRSM (Triangular Solve) kernels for single and double-precision floating-point data types, along with adjustments to GEMM (General Matrix Multiplication) and SYRK (Symmetric Rank-K Update) routines. They also addressed multi-instance performance issues on EPYC machines, improving the performance of DGEMM by modifying the blocking sizes.
software-frameworklinear-algebra-librarylinear-algebramatrix-multiplicationblis
amd/aocl-compression
Feb 2024 - Oct 2024
A software library of lossless data compression methods tuned and optimized for AMD “Zen”-based CPUs
Contributions:2 releases, 1 review, 1 PR in 7 months
data-compressionlossless-data-compression
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.